Create and query Pinecone vector indexes with hybrid search and metadata filtering.
npx skills add https://github.com/nicanac/familly-journal --skill pinecone-nicanac
Please help me install this Agent Skill. Skill: pinecone Source: https://github.com/nicanac/familly-journal/tree/main/.cursor/skills/pinecone Command: npx skills add https://github.com/nicanac/familly-journal --skill pinecone-nicanac
This Skill provides a fully managed, auto-scaling vector database solution designed for production AI applications, simplifying the deployment and management of large-scale similarity search and retrieval augmented generation (RAG) systems.
Use the pinecone skill to create a new index named 'my-documents' with a dimension of 1536 and cosine similarity.
High-intent search queries and answers about installing and using this skill.
To set up a managed vector database for RAG applications, you use this skill to create an auto-scaling index with specified dimensions and similarity metrics, requiring the pinecone-client library to store and query embeddings.
Yes, pinecone-client supports hybrid search by combining dense and sparse vectors for improved retrieval accuracy, and enables precise metadata filtering to restrict search results based on associated attributes.
The best way to achieve low-latency similarity search at scale is using a fully managed vector database, which provides auto-scaling infrastructure and maintains sub-100ms p95 query latency for production workloads.
Yes, you can use this vector database for a recommendation engine to find similar products based on user preferences and item descriptions by querying stored vector embeddings with low latency.
Yes, you need the pinecone-client library to interact with the managed vector database, as it provides the necessary interface to create indexes, ingest embeddings, and execute similarity search queries.
lewisperez999Generate text embeddings with OpenAI and search by cosine similarity in Upstash Vector or pg-vector.
rizaldiemBuild retrieval-augmented generation pipelines with vector databases and document chunking.
ivalmartChunk long-context documents and delegate analysis to an rlm-subcall subagent.
AlexiosBluffMaraStore and query embeddings with metadata filtering in a local vector database.
